Skip to main content
SpringerLink
Log in

Automatic Insulator String and Disk Detection in Aerial Images Based on a Deep Learning Approach

  • Conference paper
  • First Online:
Proceedings of the International Conference on Advanced Intelligent Systems and Informatics 2021 (AISI 2021)

Part of the book series: Lecture Notes on Data Engineering and Communications Technologies ((LNDECT,volume 100))

  • 697 Accesses

Abstract

This research uses a deep learning algorithm to detect insulator strings automatically. Besides, all available disks (or caps) in the insulator can be successfully detected, which makes the missing cap defect easily perceived by human eyes. To fulfill that, aerial images of power equipment are collected and manually annotated. Segmented insulators are blended into background images to produce synthetic images for data augmentation. The system architecture is fine-tuned based on the mask regions with a convolutional neural network. The mAP of our method is equal to 94%, and 90% for insulator and disk respectively, which outperform the YOLOv4-based approach. The experimental results depict the robustness and accurateness of the proposed approach.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 189.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 249.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Prasad, P.S., Prabhakara, B.R.: Review on machine vision based insulator inspection systems for power distribution system. J. Eng. Sci. Technol. Rev. 9, 5 (2016)

    Article  Google Scholar 

  2. Mazurek, P., Almaita, I., Khalil, N.S., Othman, A., Guizani, M.: Application of background estimation and removal techniques for the extraction of the power line components on the digital images for the automatic power line inspection systems. Pomiary, Automatyka, Kontrola 54, 698–699 (2008)

    Google Scholar 

  3. Katrasnik, G., Adrian, C., Pascual, C.: A survey of mobile robots for distribution power line inspection. IEEE Trans. Power Deliv. 25(1), 485–493 (2010)

    Article  Google Scholar 

  4. Shakhatreh, H., et al.: Unmanned aerial vehicles (UAVs): a survey on civil applications and key research challenges. IEEE Access 7, 48572–48634 (2019)

    Article  Google Scholar 

  5. Nguyen, V.N., Jenssen, R., Roverso, D.: Automatic autonomous vision-based power line inspection: a review of current status and the potential role of deep learning. Int. J. Elect. Power Energy Syst. 99, 107–120 (2018)

    Article  Google Scholar 

  6. Liu, X., Jing, C., Xiu, L., Xiren, M.: Review of data analysis in vision inspection of power lines with an in-depth discussion of deep learning technology. arXiv preprint arXiv:2003.09802 (2020)

  7. Sampedro, C., Rodriguez-Vazquez, J., Rodriguez-Ramos, A., Adrian, C., Pascual, C.: Deep learning-based system for automatic recognition and diagnosis of electrical insulator strings. IEEE Access 7, 101283–101308 (2019)

    Article  Google Scholar 

  8. Oberweger, M., Wendel, A., Bischof, H.: Visual recognition and fault detection for power line insulators. In: Proceedings of 19th Computer Vision Winter Workshop, pp. 1–8 (2014)

    Google Scholar 

  9. Wang, W., Wang, Y., Han, J., Liu, Y.: Recognition and drop-off detection of insulator based on aerial image. In: Proceedings of 9th International Symposium on Computational Intelligence and Design (ISCID), vol. 1, pp. 162–167 (2016)

    Google Scholar 

  10. Li, S., Zhou, H., Wang, G., Zhu, X., Kong, L., Hu, Z.: Cracked insulator detection based on R-FCN. In: Journal of Physics: Conference Series, vol. 1069, no. 1, p. 012147. IOP Publishing (2018)

    Google Scholar 

  11. Jiang, H., Xiaojie, Q., Jing, C., Xiu, L., Xiren, M., Shengbin, Z.: Insulator fault detection in aerial images based on ensemble learning with multi-level perception. IEEE Access 7, 61797–61810 (2019)

    Article  Google Scholar 

  12. Li, B., Wu, D., Cong, Y., Xia, Y., Tang, Y.: A method of insulator detection from video sequence. In: Proceedings of 4th International Symposium on Information Science and Engineering (ISISE), pp. 386–389 (2012)

    Google Scholar 

  13. Zhao, Z., Liu, N., Wang, L.: Localization of multiple insulators by orientation angle detection and binary shape prior knowledge. IEEE Trans. Dielectr. Electr. Insul. 22(6), 3421–3428 (2015)

    Article  Google Scholar 

  14. Wang, X., Zhang, Y.: Insulator identification from aerial images using support vector machine with background suppression. In: Proceedings of IEEE International Conference on Unmanned Aircraft Systems (ICUAS), pp. 892–897 (2016)

    Google Scholar 

  15. Prasad, P.S., Rao, B.P.: Condition monitoring of 11 kV overhead power distribution line insulators using combined wavelet and LBP-HF features. IET Gener. Transmiss. Distrib. 11(5), 1144–1153 (2016)

    Article  Google Scholar 

  16. Zhao, Z., Xu, G., Qi, Y., Liu, N., Zhang, T.: Multi-patch deep features for power line insulator status classification from aerial images. In: Proceedings of IEEE International Joint Conference on Neural Networks (IJCNN), pp. 3187–3194 (2016)

    Google Scholar 

  17. Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Proceedings of Advances Neural Information Processing System, pp. 1097–1105 (2012)

    Google Scholar 

  18. Gao, F., et al.: Recognition of insulator explosion based on deep learning. In: Proceedings of IEEE 14th International Computer Conference on Wavelet Active Media Technology and Information Processing, (ICCWAMTIP), pp. 79–82 (2017)

    Google Scholar 

  19. Ling, Z., et al.: An accurate and real-time self-blast glass insulator location method based on faster R-CNN and U-net with aerial images arXiv:1801.05143 (2018)

  20. Shanjun, L., Zhou, H., Wang, G., Zhu, X., Kong, L., Hu, Z.: Cracked insulator detection based on R-FCN. In: Journal of Physics: Conference Series, vol. 1069, no. 1, p. 012147. IOP Publishing (2018)

    Google Scholar 

  21. Siddiqui, Z.A., et al.: Robust powerline equipment inspection system based on a convolutional neural network. Sensors 18(11), 3837 (2018)

    Article  Google Scholar 

  22. Changfu, X., Bo, B., Liu, Y., Tao, F.: Detection method of insulator based on single shot multibox detector. In: Journal of Physics: Conference Series, vol. 1069, no. 1, p. 012183. IOP Publishing (2018)

    Google Scholar 

  23. Graphical image annotation tool. https://github.com/tzutalin/labelImg

  24. Kaiming, H., Xiangyu, Z., Shaoqing, R., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)

    Google Scholar 

  25. Kirillov, A., Girshick, R., Kaiming, H., Dollár, P.: Panoptic feature pyramid networks. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6399–6408 (2019)

    Google Scholar 

  26. Kaiming, H., Gkioxari, G., Dollár, P., Girshick, R.: Mask R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2961–2969 (2017)

    Google Scholar 

  27. Bochkovskiy, A., Chien-Yao, W., Hong-Yuan, M. L.: Yolov4: optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934 (2020)

  28. Ren, S., Kaiming. H, Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks (2015)

    Google Scholar 

  29. Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning, p. 526. MIT Press, Cambridge, (2016). http://www.deeplearningbook.org. Accessed19 Sept 2019

  30. Rezatofighi, H., Nathan, T., JunYoung, G., Sadeghian, A., Reid, I., Savarese, S.: Generalized intersection over union: a metric and a loss for bounding box regression. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 658–666 (2019)

    Google Scholar 

  31. Bottou, L.: Stochastic gradient descent tricks. In: Montavon, G., Orr, G.B., Müller, K.R. (eds.) Neural networks: Tricks of the trade. Lecture Notes in Computer Science, vol. 7700, pp. 421–436. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-35289-8_25

    Chapter  Google Scholar 

Download references

Acknowledgment

This work is sponsored by the National Natural Science Foundations of China (No. 61872085), the Scientific Research Project of Fujian Education Department (JK2017029, JAT190069), and the Scientific Research and Development Foundation of Fujian University of Technology (GY-Z18181, GY-Z20068, XF-X19017).

Author information

Authors and Affiliations

  1. School of Computer Science and Mathematics, Fujian University of Technology, Fuzhou, China

    Gilbert Shyirambere, Rui Xu, Fatana Jafari, Jean Bosco Ndungutse & Shi-Jian Liu

  2. Key Laboratory of Big Data Mining and Applications of Fujian Province, Fujian University of Technology, Fuzhou, China

    Shi-Jian Liu

Authors
  1. Gilbert Shyirambere
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Rui Xu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Fatana Jafari
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Jean Bosco Ndungutse
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Shi-Jian Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Information Technology Department, Cairo University, Faculty of Computers and Artificial Intelligence, Giza, Egypt

    Aboul Ella Hassanien

  2. Faculty of Electrical Engineering and Computer Science, VÅ B-Technical University of Ostrava, Ostrava-Poruba, Moravskoslezsky, Czech Republic

    Václav Snášel

  3. Fujian University of Technology, Shulin District, New Taipei, Taiwan

    Kuo-Chi Chang

  4. Faculty of Science, Helwan University, Cairo, Egypt

    Ashraf Darwish

  5. University of Salford, Manchester, UK

    Tarek Gaber

Rights and permissions

Reprints and permissions

Copyright information

© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Shyirambere, G., Xu, R., Jafari, F., Ndungutse, J.B., Liu, SJ. (2022). Automatic Insulator String and Disk Detection in Aerial Images Based on a Deep Learning Approach. In: Hassanien, A.E., Snášel, V., Chang, KC., Darwish, A., Gaber, T. (eds) Proceedings of the International Conference on Advanced Intelligent Systems and Informatics 2021. AISI 2021. Lecture Notes on Data Engineering and Communications Technologies, vol 100. Springer, Cham. https://doi.org/10.1007/978-3-030-89701-7_8

Download citation

Publish with us

Policies and ethics

Search

Navigation